activity
20162024
most citedCal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error

17 citations · 22 across the 9 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV20242 cited

DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection

Zhuoxiao Chen, Zixin Wang, Yadan Luo +2

LiDAR-based 3D object detection has seen impressive advances in recent times. However, deploying trained 3D detectors in the real world often yields unsatisfactory performance when…

cs.CV2024

Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts

Haodong Hong, Sen Wang, Zi Huang +2

Current Vision-and-Language Navigation (VLN) tasks mainly employ textual instructions to guide agents. However, being inherently abstract, the same textual instruction can be assoc…

cs.CV2023

No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling

Xuwei Xu, Changlin Li, Yudong Chen +3

Vision Transformers (ViTs) have demonstrated outstanding performance in computer vision tasks, yet their high computational complexity prevents their deployment in computing resour…

cs.CV20233 cited

Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection

Bingqing Zhang, Sen Wang, Yifan Liu +3

Current video object detection (VOD) models often encounter issues with over-aggregation due to redundant aggregation strategies, which perform feature aggregation on every frame.…

cs.CV202317 cited

Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error

Zixin Wang, Yadan Luo, Zhi Chen +2

The prevalence of domain adaptive semantic segmentation has prompted concerns regarding source domain data leakage, where private information from the source domain could inadverte…

cs.CV2021

Action2video: Generating Videos of Human 3D Actions

Chuan Guo, Xinxin Zuo, Sen Wang +4

We aim to tackle the interesting yet challenging problem of generating videos of diverse and natural human motions from prescribed action categories. The key issue lies in the abil…